Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Ronkupper/PRISMWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/ronkupper/prism/prism-whats-next)<a href="https://agentmods.dev/commands/ronkupper/prism/prism-whats-next"><img src="https://agentmods.dev/badge/commands/ronkupper/prism/prism-whats-next.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.00526 |
| Opus 5 | $0.00019 | $0.00263 |
| Sonnet 5 | $0.00008 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
prism-whats-next scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Resume the active PRISM engagement from its continuous state — this is the PRISM Desk, your single pane of glass between sessions.
Optional Master pointer or focus note (may be empty):
$ARGUMENTS
Then proceed:
- Locate the Master. Use an attached Master, the one in this project/repo
(or repo-backed
What's next), or the path/pointer above. If no Master can be found, run the SP-1 / missing-handoff recovery protocol inPRISM_core.md— do not regenerate the Master from memory. - Load the framework if it is not already active: read
PRISM_core.md(naming PRISM also auto-triggers theprismSkill, which loads the same core). - Run the SP-13 substrate self-check, then M1 (Missing Inputs) and M2 (Version Drift) against the Master and its declared attachments. Halt at HIGH severity on a missing required artifact or a version mismatch.
- Read the Master's What's next artifact and proceed from the predicted next action. If a focus was supplied above, weigh it against What's next and let the operator choose when they diverge rather than silently overriding the plan.
- Stage the next step as a card. When the next action is a dispatch, render it
as a paste-ready Execution Envelope (the ACTION surface) with its Dispatch ID;
otherwise name the next move plainly. On request, render the STATE view
(
/prism-status) instead. - If What's next is missing or stale, surface that and ask the operator rather than guessing the next action.
This command is a Claude-Skill convenience for resuming PRISM; it changes no
framework mechanic. Asking "What's next?" in plain language is equivalent, and is
the portable form on every other vendor. Its siblings cover the rest of the loop:
/prism-converge (fold returns back), /prism-status (the trajectory view), and
/prism-close (finish the engagement).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 40 lines · 38 tokens per session scan A bb3ea67e93e9
prism-whats-next is a command published in the GitHub repository Ronkupper/PRISM (5 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 526 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
plan-start
5-phase planning command: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.
adopt-roadmap.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
update-check.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
parallel
You are executing the /hydra:parallel command. Start multiple agents simultaneously in different worktrees.
board-csk
Team board — see who holds which item, claim one, hand it over, complete it.